UK Source Intelligence

by dev.workers.mazdamen.uk-source-intelligence-mcp

watch_govuk_page

MONITOR CHANGES: Register a supported canonical GOV.UK page for recurring checks and stored snapshots. Fourteen-day free trial allows 1 custom page; £4.99 one-off 30-day pilot allows 3. Initial baseline is attempted immediately; if unavailable it is queued. First snapshot is not a change event. For a one-call private digest use my_watch_changes and save next_cursor. No guaranteed check interval or built-in email or ChatGPT alert; paid keys may configure an optional signed HTTPS webhook through the API.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "watch_govuk_page"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	Full canonical https://www.gov.uk/ URL for a supported Content API page.
`api_key`	No	Optional UKSI API key (usi_...). Prefer supplying Authorization: Bearer KEY in MCP connection settings rather than exposing paid keys in tool calls.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=false, so the description carries the burden and does it well: it discloses that a baseline is attempted immediately or queued, that the first snapshot is not a change event, that there is no guaranteed check interval, and that email/ChatGPT alerts do not exist while a signed HTTPS webhook can be configured with paid keys.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action, then pricing, then behavioral caveats, then the alternative. Dense but each clause carries operational meaning; the trial/pilot pricing is the least essential element but still informs quota limits.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a write-side registration tool with no output schema, the description covers baseline behavior, change-event semantics, alerting limits, and quota constraints. The only real gap is what the tool returns on registration (identifier, watch id), which is left unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema documents both parameters. The description still adds meaning by constraining the URL to a supported canonical page and by flagging that api_key relates to paid tiers and webhook configuration, which is more than the schema alone implies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (register) and resource (supported canonical GOV.UK page) plus the effect: recurring checks and stored snapshots. The 'MONITOR CHANGES' prefix and the pointer to my_watch_changes let an agent distinguish this from related siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent to my_watch_changes when a one-call private digest is wanted, and states the trial/pilot quotas that gate usage. It does not contrast against other siblings such as page_changes or list_my_watches, so the when-not guidance is partial.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All UK Source Intelligence tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?